Estimation of the bandwidth parameter in Nadaraya-Watson kernel non-parametric regression based on universal threshold level

• Published in: Communications in statistics. Simulation and computation Vol. 52; no. 4; pp. 1476 - 1489
• Main Authors: Ali, Taha Hussein, Hayawi, Heyam Abd Al-Majeed, Botani, Delshad Shaker Ismael
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 03-04-2023; Taylor & Francis Ltd
• Subjects: Bandwidth parameter; Kernel functions; Mathematical analysis; Non-parametric regression; Nonparametric statistics; NW kernel estimator; Universal threshold
• ISSN: 0361-0918; 1532-4141
• DOI: 10.1080/03610918.2021.1884719

This paper proposes a new improvement of the Nadaraya-Watson kernel non-parametric regression estimator and the bandwidth of this new improvement is obtained depending on universal threshold level with wavelet of kernel function instead of using fixed bandwidth and variable bandwidth for geometric, arithmetic mean, range and median measurements. A simulation study is presented, including comparisons between the proposed method and five others Nadaraya-Watson kernel estimators (classical methods), as well as using real data depending on a program written in MATLAB language which was designed for this purpose. It was concluded that the proposed method is more accurate than all classical methods for all simulations and real data based on MSE criterion.